Update README.md
Browse files
README.md
CHANGED
|
@@ -9,4 +9,6 @@ This model uses the LTG-BERT architecture.
|
|
| 9 |
The model was trained on a combination of the BabyLM Dataset, the TinyStories Dataset, and generated data,
|
| 10 |
in accordance with the rules of the Stric track, and the 100M word budget.
|
| 11 |
|
|
|
|
|
|
|
| 12 |
Hyperparameters used and evaluation scores will follow in a subsequent update.
|
|
|
|
| 9 |
The model was trained on a combination of the BabyLM Dataset, the TinyStories Dataset, and generated data,
|
| 10 |
in accordance with the rules of the Stric track, and the 100M word budget.
|
| 11 |
|
| 12 |
+
The models were trained with 128 token sequence length
|
| 13 |
+
|
| 14 |
Hyperparameters used and evaluation scores will follow in a subsequent update.
|